Zobrazeno 1 - 10
of 128
pro vyhledávání: '"Marchand., Mario"'
In this work, we provide upper bounds on the risk of mixtures of experts by imposing local differential privacy (LDP) on their gating mechanism. These theoretical guarantees are tailored to mixtures of experts that utilize the one-out-of-$n$ gating m
Externí odkaz:
http://arxiv.org/abs/2410.10397
Autor:
Chen, Qi, Marchand, Mario
We use information-theoretic tools to derive a novel analysis of Multi-source Domain Adaptation (MDA) from the representation learning perspective. Concretely, we study joint distribution alignment for supervised MDA with few target labels and unsupe
Externí odkaz:
http://arxiv.org/abs/2304.02064
We revisit binary decision trees from the perspective of partitions of the data. We introduce the notion of partitioning function, and we relate it to the growth function and to the VC dimension. We consider three types of features: real-valued, cate
Externí odkaz:
http://arxiv.org/abs/2210.10781
SHAP explanations aim at identifying which features contribute the most to the difference in model prediction at a specific input versus a background distribution. Recent studies have shown that they can be manipulated by malicious adversaries to pro
Externí odkaz:
http://arxiv.org/abs/2205.15419
We significantly improve the generalization bounds for VC classes by using two main ideas. First, we consider the hypergeometric tail inversion to obtain a very tight non-uniform distribution-independent risk upper bound for VC classes. Second, we op
Externí odkaz:
http://arxiv.org/abs/2111.00062
Publikováno v:
Journal of Machine Learning Research, 2023, vol. 24, no 364, p. 1-50
Post-hoc global/local feature attribution methods are progressively being employed to understand the decisions of complex machine learning models. Yet, because of limited amounts of data, it is possible to obtain a diversity of models with good empir
Externí odkaz:
http://arxiv.org/abs/2110.13369
We derive a novel information-theoretic analysis of the generalization property of meta-learning algorithms. Concretely, our analysis proposes a generic understanding of both the conventional learning-to-learn framework and the modern model-agnostic
Externí odkaz:
http://arxiv.org/abs/2109.14595
Decision trees are popular machine learning models that are simple to build and easy to interpret. Even though algorithms to learn decision trees date back to almost 50 years, key properties affecting their generalization error are still weakly bound
Externí odkaz:
http://arxiv.org/abs/2010.07374
Deep kernel learning provides an elegant and principled framework for combining the structural properties of deep learning algorithms with the flexibility of kernel methods. By means of a deep neural network, we learn a parametrized kernel operator t
Externí odkaz:
http://arxiv.org/abs/1905.12131
Autor:
Drouin, Alexandre, Raymond, Frédéric, St-Pierre, Gaël Letarte, Marchand, Mario, Corbeil, Jacques, Laviolette, François
Antimicrobial resistance is an important public health concern that has implications in the practice of medicine worldwide. Accurately predicting resistance phenotypes from genome sequences shows great promise in promoting better use of antimicrobial
Externí odkaz:
http://arxiv.org/abs/1612.01030